Humans are social agents and the social dimension is an important aspect of human cognition. One challenge facing the realization of artifacts and artificial agents that posses humanlike cognition abilities is to implement human-like interactive capabilities into them. Natural Language Processing is one of the earliest applications of AI techniques because of the importance of language in shaping human cognitive and interactive capabilities. Nevertheless nonverbal communication is starting to gain more importance specially in the domains of HRI and ECA because natural human-human communications are known to utilize a variety of nonverbal interaction protocols. This paper proposes a new adaptation algorithm for interactive agents that aims to develop agents that can learn and adapt their theory of mind concerning nonverbal interaction in real-time during actual interactions. The proposed method utilizes elements of the theory of theory and the theory of simulation to guide the adaptation process. A proof of concept simulation experiment with the proposed system is also illustrated.

Gaze behavior is one of the most important nonverbal behaviors during human-human close encounters. For this reason, many researchers in natural human-robot interaction focus on developing robots that can achieve human-like gaze behavior. Many approaches have been proposed to achieve this natural gaze behavior based on accurate analysis of human behaviors during natural interactions. One limitation of most available approaches is that the behavior is hardwired to the robot and learning techniques are used only, if ever, for adjusting the parameters of the behavior. In this paper we propose and evaluate a different approach in which the robot learns natural gaze behavior by watching natural interactions between humans. The proposed approach uses the LiEICA architecture developed by the authors and is completely unsupervised which leads to grounded behavior. We compare the resulting gaze controller with a state-of-the-art gaze controller that achieved human-like behavior and show that the proposed approach leads to a more natural gaze behavior based on subjective evaluations of subjects.

Abstract The IAM (Interaction Adaptation Manager) algorithm was recently proposed to learn the optimal parameters of a hierarchical dynamical system incrementally through interacting with other agents given that the structure of the system is known (the number of processes in each layer and their interconnections) and that the agent knows how to interact in all roles except the one it is learning (e.g. an agent learning to listen should know how to speak). This paper presents an algorithm for learning the structure of a hierarchical dynamical system representing the interaction protocol at various timescales and using multiple modalities relaxing these two constraint. The proposed system was tested in a simulation environment in which rich human-like agents are interacting and showed accurate recognition of the interaction structure using few training examples. The learned structure showed acceptable performance that allowed subsequent application of the adaptation algorithm to converge to a good solution using as few as 15 interactions. 1

Abstract Human-Robot Interaction (HRI) is a growing field of research that targets the development of robots which are easy to operate, more engaging and more entertaining. Natural human-like behavior is considered by many researchers as an important target of HRI. Research in Human-Human communications revealed that gaze control is one of the major interactive behaviors used by humans in close encounters. Human-like gaze control is then one of the important behaviors that a robot should have in order to provide natural interactions with human partners. To develop human-like natural gaze control that can integrate easily with other behaviors of the robot, a flexible robotic architecture is needed. Most robotic architectures available were developed with autonomous robots in mind. Although robots developed for HRI are usually autonomous, their autonomy is combined with interactivity, which adds more challenges on the design of the robotic architectures supporting them. This paper reports the development and evaluation of two gaze controllers using a new cross-platform robotic architecture for HRI applications called EICA (The Embodied Interactive Control Architecture), that was designed to meet those challenges emphasizing how low level attention focusing and action integration are implemented. Evaluation of the gaze controllers revealed human-like behavior in terms of mutual attention, gaze toward partner, and mutual gaze. The paper also reports a novel Floating Point Genetic Algorithm (FPGA) for learning the parameters of various processes of the gaze controller.

Abstract. Behavior generation in humans and animals usually employs a combination of bottom-up and top-down patterns. Most available robotic architectures utilize either bottom-up or top-down activation including hybrid architectures. In this paper, we propose a behavior generation mechanism that can seamlessly combine these two strategies. One of the main advantages of the proposed approach is that it can naturally combine both bottom-up and top-down behavior generation mechanisms which can produce more natural behavior. This is achieved by utilizing results from the theory of simulation in neuroscience which tries to model the mechanism used in human infants to develop a theory of mind. The proposed approach was tested in modeling spontaneous gaze control during natural face to face interactions and provided more natural, human-like behavior compared with a state-of-the-art gaze controller that utilized a bottom-up approach. 1

Abstract — In this paper, we present our efforts toward building interactive robots that can learn how to interact naturally with human partners in different environments and contexts. The main feature of our approach is that it relies completely on unsupervised learning and time series analysis techniques that allow the robot to build its own interaction protocol representation from the bottom up. The final controller of the robot learned this way is a hierarchy of either dynamical systems or probabilistic networks with complexity that is automatically adjusted to the interaction protocol to be learned. We report two examples of applying this technique to learn an explicit interaction protocol in a master-slave settings (guided navigation) and an implicit protocol in a teammate settings (a listener robot). I.

to whom it may concern We hereby certify that this is a typical copy of the original Doctoral Thesis written

Abstract — Change point discovery is an important problem in data mining and industrial systems. Different approaches have been proposed and some of the most promising approaches are based on singular spectrum analysis (SSA). These algorithms have the advantages of requiring no ad-hoc tuning for different types of signals and having a built-in noise attenuation mechanism. In this paper we try to unify these approaches and present a novel method for comparing change point discovery algorithms. We then use the proposed method to compare different SSA based change point discovery algorithms. Even though we focused on comparing only SSA based algorithms, the proposed metric applicable to any kind of change point discovery algorithm and have the advantages of requiring no localization steps, and being independent of any predefined thresholds (unlike traditional metrics). I.

Abstract. During face to face interactions, the emotional state of each participant is greatly affected by the behavior of other participants and how much this behavior conforms with common protocols of interaction in the society. Research in human to human interaction in face to face situations has uncovered many forms of synchrony in the behavior of the interacting partners. This includes factors as body alignment, entrainment of verbal behavior. Maintenance of these kinds of synchrony is essential to keep the interaction natural and to regulate the affective state of the interacting partners. In this chapter we examine the interplay between one partner’s use of interaction protocols, maintenance of synchrony and the emotional response of the other partner in the two way interactions. We will first define the notion of interaction protocol and relate it with the Reactive Theory of Intention and Low Level Emotions. We will then show empirically that the use of suitable interaction protocols is essential

Abstract — Complex systems involve the interaction between many processes that may or may not have causal relations to each other. In such systems, discovering causal relations can provide significant insights into the internals of the system and facilitate fault discovery and recovery procedures. In this paper, we provide a novel causality detection algorithm based on robust singular spectrum transform that combines features of autoregressive modeling and perturbation analysis. The proposed approach was evaluated using both synthetic and real data and was shown to provide superior performance to the standard linear Granger-causality test. It also provides a natural way to detect common causes that may give false positives in other causality tests. I.